© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 155358
    Prev
    Next
    INDEX
    Explanations

    word then word

    np_acts-logits-general · gemini-2.5-flash-lite

    Calculation, potentially far, already been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    特
    0.41
    ROUND
    0.41
     USING
    0.41
     enteral
    0.41
    oblig
    0.40
    sendKeyDown
    0.40
    t
    0.40
    시
    0.39
     راح
    0.39
    協会
    0.39
    POSITIVE LOGITS
     والب
    0.47
     हल्के
    0.42
    dia
    0.42
     parámetro
    0.42
     Zeke
    0.41
     Huck
    0.41
     এবারের
    0.40
     ermög
    0.40
     وهذه
    0.40
     hinsichtlich
    0.40
    Activations Density 0.002%

    No Known Activations